• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.35 no.6
• /
• pp.556-561
• /
• 2022

Computational material science as an application of Density Functional Theory (DFT) to the discipline of material science has emerged and applied to the research and development of energy materials and electronic materials such as semiconductor. However, there are a few difficulties, such as generating input files for various types of materials in both the same calculating condition and appropriate parameters, which is essential in comparing results of DFT calculation in the right way. In this tutorial status report, we will introduce how to create crystal structures and to prepare input files automatically for the Vienna Ab initio Simulation Package (VASP) and Gaussian, the most popular DFT calculation programs. We anticipate this tutorial makes DFT calculation easier for the ones who are not experts on DFT programs.

• Korean Journal of Materials Research
• /
• v.33 no.4
• /
• pp.164-174
• /
• 2023

The bandgap characteristics of semiconductor materials are an important factor when utilizing semiconductor materials for various applications. In this study, based on data provided by AFLOW (Automatic-FLOW for Materials Discovery), the bandgap of a semiconductor material was predicted using only the material's compositional features. The compositional features were generated using the python module of 'Pymatgen' and 'Matminer'. Pearson's correlation coefficients (PCC) between the compositional features were calculated and those with a correlation coefficient value larger than 0.95 were removed in order to avoid overfitting. The bandgap prediction performance was compared using the metrics of R² score and root-mean-squared error. By predicting the bandgap with randomforest and xgboost as representatives of the ensemble algorithm, it was found that xgboost gave better results after cross-validation and hyper-parameter tuning. To investigate the effect of compositional feature selection on the bandgap prediction of the machine learning model, the prediction performance was studied according to the number of features based on feature importance methods. It was found that there were no significant changes in prediction performance beyond the appropriate feature. Furthermore, artificial neural networks were employed to compare the prediction performance by adjusting the number of features guided by the PCC values, resulting in the best R² score of 0.811. By comparing and analyzing the bandgap distribution and prediction performance according to the material group containing specific elements (F, N, Yb, Eu, Zn, B, Si, Ge, Fe Al), various information for material design was obtained.